A Research Infrastructure for Real-Time Evaluation of Predictive Algorithms for Intensive Care Units

摘要：

　　In the medical informatics,most algorithms for clinical settings are initially developed and evaluated using retrospective data.However,researchers often lack convenient methods to validate their algorithms with real-time patient data.To bridge the gap between research and clinical applications,we present a research infrastructure that grants researchers access to real-time clinical data without disturbing patient care.The infrastructure is based on the Healtii Level Seven (HL7) messaging standard.Admission/discharge/transfer and obseiration result messages (?mtaining lab test results and vital signs) are deidentified in real-time on a hospital network and subsequently transmitted to a research network.Then the processing duster on ttie research network can process incoming de-identified.data for a wide variety of applications.In the research network,a translator for converting Ihe HL7 data stream into MATLAB format is created for convenient algoritiim evaluation.As an example,we evaluated a hypotension predictor using our realtime testing enviranmoit Our infrastructure can easily be replicated in other institutions and has the potential to benefit many researchers In translattonal medicine.

关键词： real-time medical data algorithm evaluation dynamic de-identification Health Level Seven messaging standard MATLAB-Java interface

作者: Zhengbo Zhang Joon Lee Daniel J. Scott Li-wei Lehman Roger G.Mark

作者单位: Department of Biomedical Engineering, Chinese PLA General Hospital, Beijing 100853, China; Harvard-M Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambr Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambr

会议类型: 国际会议

会议名称: 2013 ICME International Conference on Complex Medical Engineering(2013 ICME复合医学工程国际会议)

会议地点: 北京

会议语种:英文

页码: 109-114

在线出版日期: 2013-05-25（万方平台首次上网日期，不代表论文的发表时间）